Rahka commited on
Commit
2e33e0b
·
1 Parent(s): fdc35cd

training_172e61b

Browse files
added_tokens.json CHANGED
@@ -1,4 +1,5 @@
1
  {
2
- "[corona]": 30000,
3
- "[landtagswahl]": 30001
 
4
  }
 
1
  {
2
+ "Corona": 31104,
3
+ "corona": 31102,
4
+ "landtagswahl": 31103
5
  }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "bert-base-german-cased",
3
  "architectures": [
4
  "BertModel"
5
  ],
@@ -15,11 +15,12 @@
15
  "model_type": "bert",
16
  "num_attention_heads": 12,
17
  "num_hidden_layers": 12,
 
18
  "pad_token_id": 0,
19
  "position_embedding_type": "absolute",
20
  "torch_dtype": "float32",
21
  "transformers_version": "4.25.1",
22
  "type_vocab_size": 2,
23
  "use_cache": true,
24
- "vocab_size": 30002
25
  }
 
1
  {
2
+ "_name_or_path": "dbmdz/bert-base-german-cased",
3
  "architectures": [
4
  "BertModel"
5
  ],
 
15
  "model_type": "bert",
16
  "num_attention_heads": 12,
17
  "num_hidden_layers": 12,
18
+ "output_past": true,
19
  "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.25.1",
23
  "type_vocab_size": 2,
24
  "use_cache": true,
25
+ "vocab_size": 31105
26
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93c198112d1c0301a9cdc20432209c6aaaf11322a0893c57198c9dcd5cd13072
3
- size 436399917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48e551a668bb783bd77256cdea76f4f7cc9e293497daeba181a2441a9dc6c5aa
3
+ size 439788333
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,9 +1,12 @@
1
  {
2
  "cls_token": "[CLS]",
 
3
  "do_lower_case": false,
4
  "mask_token": "[MASK]",
 
5
  "model_max_length": 512,
6
- "name_or_path": "bert-base-german-cased",
 
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "special_tokens_map_file": null,
 
1
  {
2
  "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
  "do_lower_case": false,
5
  "mask_token": "[MASK]",
6
+ "max_len": 512,
7
  "model_max_length": 512,
8
+ "name_or_path": "dbmdz/bert-base-german-cased",
9
+ "never_split": null,
10
  "pad_token": "[PAD]",
11
  "sep_token": "[SEP]",
12
  "special_tokens_map_file": null,
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff